Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76727
    Prev
    Next
    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lees
    -0.07
    ияти
    -0.07
    /View
    -0.07
    encji
    -0.07
     Bays
    -0.07
    /Re
    -0.07
     Encyclopedia
    -0.07
     Neste
    -0.07
     aanwij
    -0.07
     القول
    -0.07
    POSITIVE LOGITS
    6
    0.08
    welt
    0.07
    BEGIN
    0.07
    28
    0.07
    029
    0.07
     concorr
    0.07
    19
    0.07
    9
    0.07
    594
    0.07
     Discovery
    0.07
    Activations Density 0.012%

    No Known Activations